Arao AI
Back to search results

Hy-Memory-30B-A3B · Q4_K_M

Start a discussion
Apple M2 UltraOllama v0.32L2 Cross-framework verified

This page aggregates 1 real-world runs of Hy-Memory-30B-A3B (Q4_K_M) on Apple M2 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

134.47 tok/s

Decode

Decode speed

706.31 tok/s

Prefill

Prefill speed

0.52 s

TTFT

Time to first token

53.76 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. llama.cpp · IQ2_XS Decode 240.85 · Prefill 1025.78 ·
  2. llama.cpp · Q2_K Decode 207.84 · Prefill 1139.16 ·
  3. Ollama · Q2_K Decode 187.09 · Prefill 853.49 ·
  4. Ollama · Q4_K_M (current)Decode 134.47 · Prefill 706.31 ·

Core figures

Decode (avg)
134.47 tok/s
Prefill (avg)
706.31 tok/s
TTFT (avg)
0.52 s
VRAM (avg)
53.76 GB
MTP acceptance rate
—
TTFB
1.08 GB
Power draw
127.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Hy-Memory-30B-A3B
Quantization
Q4_K_M
Framework
Ollama
Version
v0.32
Context length
32768 tokens
Batch size
256
GPU layers
33
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
Apple M2 Ultra
Measured VRAM (avg)
53.76 GB
OS
macOS 26.1
Power draw
127.4 W

Get started

Original model resources

Base model resources may not match this quantization. Use the verified deployment weights above when available.

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.32 · macOS 26.1 · 32768 ctx

    134.47 tok/s

    Decode

    706.31 tok/s

    Prefill

    0.52 s

    TTFT

    53.76 GB

    VRAM

    —

    MTP

    127.4 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=103 running model_id=87 at Q4_K_M